Note: Google Colab with GPU, AWS Sagemaker, Azure, Data Bricks, OpenAI, Bitbucket/Github, Python will be used during this course.

Tests and assessments will be done for each session, materials will be shared after end of each session.

• Introduction to AIML: (40 Mins X 1 session)

o How service industry is using AIML (Role of a DataScientist, Available Hyperscalers, AIML Applications)

o Overview of different types of machine learning (supervised, unsupervised, reinforcement learning)

• Mathematical Foundations with python: (40 Mins X 1 session)

o Linear algebra

o Probability and statistics

o Calculus basics

• Programming, Math and Algorithms Foundation: (40 Mins X 2 sessions)

o Python Libraries

o Numpy, Scipy, Pandas, Matplotlib

o Data processing and visualization

o Feature selection and extraction

o Intuitive and simple algorithms

o Classification and Regression Problems

o Dimensionality Reduction

• Data Preprocessing: (40 Mins X 1 sessions)

o Data cleaning

o Feature engineering

o Data normalization and scaling

• Supervised Learning: (40 Mins X 1 session)

o Linear regression

o Logistic regression

o Decision trees

o Support vector machines (SVM)

• Unsupervised Learning: (40 Mins X 1 session)

o Clustering algorithms (K-means, hierarchical clustering)

o Principal component analysis (PCA)

• Deep Learning: (40 Mins X 3 sessions)

o Introduction to DL

o Pytorch, TensorFlow & Keras

o Convolutional Neural Networks

o Autoencoders

o Time series

o RNN

o LSTM

o GRU

o Recommendation systems

• Advanced Topics: (40 Mins X 2 sessions)

o Transfer Learning

o Deployment and practical issues

o GANs

o Computer Vision

o ML in speech

o Advanced NLP

• Exercises: (40 Mins X 6 sessions)

o Data Pre-processing, Manipulation and Visualization

o Solving classification and regression problems

o k-NN classifier, linear classifier, decision tree, bagging classifier, voting classifier, linear regression and logistic regression

o Features extraction, normalization, transformation

o Web scaping and NLTK

o Dimensionality reduction and simple PCA o Text representation, generation and classification

o Support vector machine

o Ensemble methods – random forest, XG-Boost

o NLP and speech processing

o Training, validation and testing

o Avoid overfitting

o K-Means clustering

o PCA EigenFaces

o Reconstruction of Images

o Pytorch

o Tensorflow and Keras

o Recurrent Neural Network

o Time Series Application

o Transfer Learning and Fine Tuning

o Sentiment Analysis

o Emotion recognition from face and speech

o Finding the optimal route

o Image augmentation, segmentation and classification

o Object detection

o Video processing

o Transformers BERT, GPT fine tuning

o Hugging face transformers

o LLMs-chat GPT, Llama

o LangChain & RAG

• Support on Lab Setup – AI Models deployment, Testing, Debugging